memory_migrate
Manually trigger migration from legacy JSON store to sql.js Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects without managing directory layout, or (c) the .swarm/memory.db ...
This record as markdown: /tools/io-github-ruvnet-claude-flow/memory-migrate.md
What memory_migrate does on Claude Flow
AI agents invoke memory_migrate to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why memory_migrate is rated High
This tool executes a migration process that reads from a legacy JSON store and writes to a sql.js database. It is not a simple read or write — it orchestrates a transformation and transfer of data across storage systems, which constitutes an execution of a multi-step operation. While it modifies data, the primary action is triggering a pipeline (migration), not a single write.
From the tool's definition 'Manually trigger migration from legacy JSON store to sql.js' — triggers a data migration operation that transforms and moves data between storage backends
Attacks that exploit this kind of access
The rule that runs memory_migrate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For memory_migrate, this is the rule to start with:
memory_migrate stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every memory_migrate call is checked against it from then on.
Questions about memory_migrate
Manually trigger migration from legacy JSON store to sql.js Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects without managing directory layout, or (c) the .swarm/memory.db audit trail. For one-shot file I/O, native Read/Write is fine. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for memory_migrate: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Flow. Nothing to install.
memory_migrate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the memory_migrate rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for memory_migrate. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
memory_migrate is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
Across the catalogue